Knowing which telemetry parameters are behaving accordingly and those which are behaving out of the ordinary is vital information for continued mission success. For a large amount of different parameters, it is not possible to monitor all of them manually. One of the simplest methods of monitoring the behavior of telemetry is the Out Of Limit (OOL) check, which monitors whether a value exceeds its upper or lower limit. A fundamental problem occurs when a telemetry parameter is showing signs of abnormal behavior; yet, the values are not extreme enough for the OOL-check to detect the problem. By the time the OOL threshold is reached, it could be too late for the operators to react. To solve this problem, the Automated Telemetry Health Monitoring System (ATHMoS) is in development at the German Space Operation Center (GSOC). At the heart of the framework is a novel algorithm for statistical outlier detection which makes use of the socalled Intrinsic Dimensionality (ID) of a data set. Using an ID measure as the core data mining technique allows us to not only run ATHMoS on a parameter by parameter basis, but also monitor and flag anomalies for multi-parameter interactions. By aggregating past telemetry data and employing these techniques, ATHMoS employs a supervised machine learning approach to construct three databases: Historic Nominal data, Recent Nominal data and past Anomaly data. Once new telemetry is received, the algorithm makes a distinction between nominal behaviour and new potentially dangerous behaviour; the latter of which is then flagged to mission engineers. ATHMoS continually learns to distinguish between new nominal behavior and true anomaly events throughout the mission lifetime. To this end, we present an overview of the algorithms ATHMoS uses as well an example where we successfully detected both previously unknown, and known anomalies for an ongoing mission at GSOC.
As part of the Automated Telemetry Health Monitoring System (ATHMoS) being developed at GSOC, we performed an investigation into potential applications of artificial neural networks to our existing health monitoring system. In the end, we have created an experimental module which uses several deep learning neural networks to augment our existing data analysis algorithms. The module accomplishes three things; automatic feature extraction, anomaly detection, and telemetry prediction. Automatic feature extraction is used to determine numerical values which represent a time window of a single parameters telemetry data, then, using these abstract numeric values we augment our existing so-called feature vectors used in our ATHMoS anomaly detection system to provide additional information in the anomaly detection.Additionally, we use the same type of neural network to perform anomaly detection on each telemetry parameter in order to take an ensemble machine learning approach to detecting anomalies in telemetry. By combining the results of the neural network with our existing (nonneural network) anomaly detection algorithms, we can provide a more robust classification of whether or not new data should be flagged as anomalous.Lastly, we've created a neural network which given the most recent orbit data, can predict the general behaviour of a telemetry parameter over the next four and a half hours. Thus, if the prediction we obtain is off from the usual nominal behaviour of the telemetry parameter, we flag it and label it as a potential future anomaly -thereby performing anomaly prediction.Adding these experimental neural network capabilities to work concomitantly with the already existing anomaly detection modules which ATHMoS is comprised of, has already shown to be beneficial by providing new insights into the data as well as offering a more robust approach to anomaly detection via ensemble machine learning. Here we present an overview of a year long study into applying neural networks to telemetry monitoring and discuss in detail the way in which the three applications described above are being added to the current anomaly detection system at GSOC.
As technology evolves and the complexity of satellites and the amount of available telemetry increases, the manual inspection of thousands of parameters in detail per satellite becomes less and less manageable. While automated processes such as Out-Of-Limit (OOL) checks, which verify if a parameter exceeds an upper or lower threshold, exist, they come with the drawback of needing to be defined manually and often being very coarse to detect subtle changes in the telemetry. As this is a known problem, many space agencies are developing anomaly detection systems using machine learning methods. We found that the main difficulty in developing such an algorithm, as has been done for the Automated Telemetry Health Monitoring System (ATHMoS) at German Space Operations Center (GSOC), is minimizing the number of false positives while still detecting anomalies at a sufficiently high rate. Also, computational cost needs to be minimized since the detection algorithm needs to run at least once per day for all parameters.Considering these important constraints specific to automatic anomaly detection for satellite telemetry, we analyse several algorithms commonly used, namely the LOF and LoOP algorithms, as well as, in more detail, the novel algorithm developed at GSOC named Outlier Probability Via Intrinsic Dimension (OPVID) with regards to these constraints. To this extent, we will use both academic and custom benchmarks based on artificial data and historic satellite telemetry to highlight the difficulties as well as provide solutions for choosing the right algorithms and their parameters for the wanted results.In addition to the analysis of the different algorithms for these benchmarks with mostly predefined features used as the algorithm input, we also want to provide a compact analysis of different features unique to their use case for satellite telemetry as an input to the OPVID algorithm. The results can also be extrapolated for various other algorithms. In an operational use case, these features need to be generic enough to describe every available telemetry parameter and, at the same time, provide a context for the engineers as the automated system should complement the operations team. In the result, we will see that the selection of the features has a large effect on both the false positive and true positive rate and is one of the keys to designing an anomaly detection system for an operational use case. NomenclatureATHMoS Automated Telemetry Health Monitoring System GSOC German Space Operation Center LOF Local Outlier Factor (outlier detection algorithm) LoOP Local Outlier Probability (outlier detection algorithm) LSTM Long Short Term Memory ID Intrinsic Dimension (a type of statistical quantity assigned to a data point and data set) IDOS Intrinsic Dimension Outlier Score (outlier detection algorithm) OPVID Outlier Probability Via Intrinsic Dimension (outlier detection algorithm)
We begin to see an increase in the diversity of today's space missions: Small studentdesigned satellites, unique scientific missions and fleets of commercial spacecraft are just a few of those mission types. In order to cater for new demands on the ground system and to offer customer-tailored solutions we started to rethink the foundations of the German Space Operations Center (GSOC) ground system in terms of a service-oriented architecture approach using standardized technology, mainly CCSDS Mission Operations services. We show how we modularize our ground system, identify and clearly name the mission functions present in the current system complete with timing information and data size requirements. We illustrate this process by employing a concrete prototypical mission with involvement across all departments from antenna control, data processing to mission planning and flight dynamics, and hint at the challenges encountered along the way. The chosen technical solution is motivated and explained, and aspects of deployment, performance, and security are discussed. Nomenclature
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.